JP2868909B2 - Fingerprint collation device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a fingerprint collating apparatus for comparing an input fingerprint image with a dictionary pattern stored in a dictionary to identify the user.

In recent years, with the introduction of computers into a wide range of social systems, stakeholders have been interested in system security. Many questions have been raised from the aspect of security assurance regarding ID cards and passwords that have been used as means for entering a computer room or confirming the identity of a terminal when using a terminal. On the other hand, fingerprints are considered to be the most powerful means of personal identification because they have two major characteristics, that is, everyone's identity and lifelong invariance, and much research and development has been conducted on a simple personal identification system using fingerprints. I have.

[0003]

2. Description of the Related Art FIG. 6 is a conceptual diagram showing the configuration of a conventional fingerprint collating apparatus. First, the operation at the time of registration will be described. A finger is pressed against the fingerprint sensor 1 to detect a fingerprint pattern, and is converted into digital data by an A / D converter (not shown) in the fingerprint sensor 1. The converted digital data (fingerprint data) is converted into binary data “0” and “1” by the subsequent binarization circuit 2 and stored in the frame memory 3.

[0004] The fingerprint data stored in the frame memory 3 is sequentially read out, and then enters a feature information extraction unit 4 where feature information is extracted. Here, the characteristic information is, for example, the one shown in FIG.
A branch point as shown in (a) or an end point as shown in (b). A fingerprint can be specified based on where and how many such branch points and end points exist. The extracted feature information is stored in the fingerprint dictionary storage unit 5. The above operation is repeated for a plurality of individuals, and the characteristic information of the individuals is stored in the fingerprint dictionary storage unit 5.

[0005] When the registration of the characteristic information amount in the fingerprint dictionary storage unit 5 is completed in this way, an operation for collating the fingerprint of the individual is started. In the case of collation, a finger (a finger previously used for registration, for example, an index finger) is put on the fingerprint sensor 1, and then the user enters his / her ID number using a numeric keypad (not shown). As a result,
The collating unit 6 determines the search range of the fingerprint dictionary storage unit 5 based on the ID number and reads it out at the time of collation, thereby narrowing the search range.

A fingerprint pattern is detected in the same manner as at the time of registration, and is converted into digital data by an A / D converter (not shown) in the fingerprint sensor 1. The converted digital data is converted into binary data “0” and “1” by the following binarization circuit 2 and stored in the frame memory 3.

The collation unit 6 reads the fingerprint image for collation stored in the frame memory 3 and the characteristic information for each individual stored in the fingerprint dictionary storage unit 5 and performs collation (pattern matching) of both. . When the number of matching feature patterns is equal to or greater than a predetermined number, it is determined that the fingerprints match.

Next, regarding the pattern matching operation,
This will be described in more detail. FIG. 8A shows a fingerprint image read by the fingerprint sensor 1, binarized by the binarization circuit 2, and stored in the frame memory 3. In the figure, the hatched area is a ridge line (mountain line), and the white area is a valley line. The feature information extraction unit 4 extracts a feature point from the fingerprint image, and displays a fingerprint image (feature pattern) centered on the feature point in a window (window).
Cut out multiple pieces.

Here, when cutting out the window, first, as shown in FIG. 9, the input image is divided into several small areas in advance, and the area is closer to the center of the input image in order (arrows in the figure). Search for feature points and register as windows.

FIG. 8B shows a characteristic pattern as a fingerprint dictionary. In the figure, W is a positioning window, and the remaining 1 to 6 are windows extracted around the positioning window W. This positional relationship is stored in the fingerprint dictionary storage unit 5 as a dictionary while keeping the positional relationship.

At the time of collation, the collation unit 6 performs pattern matching on the input fingerprint image in the window of the fingerprint dictionary.
The fingerprint dictionary is divided into one positioning window W and a plurality of peripheral windows for comparison. First, the positioning window W is scanned with respect to the fingerprint image to perform pattern matching,
The moving amount of the input image with respect to the registered image is grasped. Thereafter, the collation window is shifted by the amount of movement of the positioning window for collation. FIG. 8C shows the state of pattern matching. In the figure, H is the read fingerprint image. The positioning window W is scanned with respect to the fingerprint image to search for a matching pattern, and the amount of movement is remembered at the matching position. Then, when the remaining moving window is moved by the same moving amount, the state shown in FIG. When performing this pattern matching, the matching window is two-dimensionally scanned by a small amount to perform pattern matching in order to cope with distortion due to softness of human skin.

[0012]

In the fingerprint matching method based on the moving window method as described above, a binary image near a feature point of a fingerprint is cut out as a window and registered as a dictionary (feature pattern). At the time of registration, the input image is divided into several small regions in advance, and feature points are searched in order from the small region near the center of the input image, and registered as a window.

For this reason, there has been a problem that a window that is stable with respect to thickening, thinning or fading of the pattern due to sweating or roughening of the fingertip is not always preferentially selected.

Although not a moving window method, a method has been proposed in which feature points are extracted using each of a plurality of multivalued images obtained by a plurality of impressions, and feature points having a high appearance frequency are preferentially selected. (JP-A-61-272886).

However, in this method, it is necessary to perform positioning between the imprinting screens each time and to correspond the selected feature points, and there is a problem that the processing time increases.

On the other hand, the present applicant proposes a method of extracting a feature point using each of a plurality of binary images in one printing process and preferentially selecting a feature point having a high appearance frequency. (Japanese Patent Application No. 63-313533, Japanese Patent Application No. 01
-253458). According to this method, there is an advantage that correspondence between feature points is easy.

However, the problem of an increase in processing time due to repeated extraction of feature points for each of a plurality of screens has not been solved.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and an object of the present invention is to provide a fingerprint matching apparatus capable of shortening the processing time while preferentially selecting feature points having a high frequency of appearance. The purpose is.

[0019]

FIG. 1 is a block diagram showing the principle of the present invention. 6 are denoted by the same reference numerals. In the figure, 1 is a fingerprint sensor for inputting a fingerprint image, 10 is a binarization circuit which receives the output of the fingerprint sensor 1 and performs binarization by comparing it with a plurality of thresholds.
Is a first binarization memory for storing a fingerprint image for registration of the binarization circuit 10, and 12 is a feature extraction unit that receives an output of the first binarization memory 11 and extracts and stores a feature point. Part, 13
Is a second binarization memory for storing a plurality of fingerprint images for collation obtained by different threshold values of the binarization circuit 10.

Reference numeral 14 denotes a window image in the vicinity of a feature point of the first binarization memory 11 and a window image in a region corresponding to an arbitrary fingerprint image for collation stored in the second binarization memory 13. A comparison unit 15 that stores the comparison result of the comparison unit 14 and evaluates the stability of the feature points stored in the feature extraction unit 12 as a fingerprint dictionary; Is a fingerprint dictionary storage unit that stores the feature points selected by the stability evaluation unit 15 as a fingerprint dictionary. Department.

[0021]

First, the image binarized using the reference threshold is converted to the first image.
The feature point is extracted from the binary image and stored in the feature extracting unit 12. Next, the binarized image is stored in the second binarization memory 13 for each threshold value by using a plurality of threshold values which are shifted up and down around the reference threshold value. Then, the comparing unit 14 sets the first binarized memory 11
Is compared with a window image of a corresponding area of an arbitrary fingerprint image for collation stored in the second binarization memory 13, and the stability evaluation unit 15 A window having a small matching error is used as a feature pattern based on the comparison result.

With such a configuration, windows that are stable against changes in the state of sweating of the fingertips, and fat, thin, or faint patterns due to seasonal changes in the state of the fingertips are preferentially registered as a dictionary. The processing time can be shortened while preferentially selecting feature points having a high appearance frequency.

[0023]

Embodiments of the present invention will be described below in detail with reference to the drawings.

First, the principle of the present invention will be described in detail. FIG. 2 is a diagram showing a relationship between a fingerprint image and a fingerprint sensor output waveform. As shown in the figure, the fingerprint image includes an image in which a sweat gland a exists, an image in which a blur b exists, an image in which a partial sweat part c exists in addition to the sweat gland a, and a normal image.

The arrow mark in the drawing indicates the scanning direction. The output waveform of the fingerprint sensor 1 for each fingerprint image is shown in the lower row. As is clear from the figure, the output level is smaller in the portion where the sweat gland a and the blur b are present than in the original ridge portion. On the other hand, the output level increases in the sweating section shown in FIG. For this reason, it is also clear that if there is sweating, the binarization threshold value obtained from the average density of the small section or the like increases in comparison with the surrounding small sections. L1 to L3 in the figure are binarization thresholds. L1 is a normal threshold value.

For this reason, voids (cracks) and disconnections are generated in portions that should be included in the ridges. Therefore,
A plurality of new binarization thresholds are set by uniformly multiplying the binarization threshold obtained from the average density of the small section by a certain coefficient, and the binarization results by the respective thresholds are compared.

In a stable ridge position without sweat glands or blurring,
While the change in the number of white pixels due to the difference in the binarization threshold is relatively gentle, the number of white pixels greatly changes in a part where sweat glands and fading are severe compared to the surroundings.

FIG. 3 is a diagram showing the relationship between the binarization threshold and the number of white pixels. The vertical axis indicates the number of white pixels, and the horizontal axis indicates the binarization threshold.
As the binarization threshold is increased (corresponding to increasing the level of the threshold L in FIG. 2), the number of white pixels naturally decreases, but the decrease changes greatly. Therefore, the region A where the binarization threshold is large can be said to be an unstable region. On the other hand, the region from the region where the binarization threshold is low to the region where the binarization threshold is a certain value is a region where the number of white pixels is almost constant. This area B can be said to be a stable area.

Therefore, by comparing a plurality of binary images obtained by different binarization threshold values with each other, a stable ridge portion and an unstable ridge portion can be obtained from a multi-value image of one screen obtained by one impression. It is possible to achieve the object of the present invention of separating the line portion.

FIG. 4 is a block diagram showing the configuration of an embodiment of the present invention. 1 are denoted by the same reference numerals. In the figure, reference numeral 18 denotes a thinning unit for reading out the binary image for registration stored in the first binary memory 11 and performing a thinning process. The thinning unit 18 removes unnecessary whiskers of a fingerprint image and clarifies a fingerprint pattern.

The feature extracting unit 12 extracts feature information from the binary image thinned by the thinning unit 18.
2a and a feature point storage memory 12b that stores the feature points extracted by the feature extraction circuit 12a and the vicinity thereof as a feature pattern window. Other configurations are shown in FIG.
Is the same as The operation of the device configured as described above is shown in FIG.
The operation will be described with reference to the flowchart of FIG.

[0032] First, enter the registration images in the fingerprint sensor 1 (S1), in the binarizing circuit 10 using the reference threshold TH _S 2
The value is converted (S2). The binarized image is once converted to the first 2
It is stored in the value memory 11. Next, the binarized memory 11
After the entered image is read, the thinning unit 18 performs a thinning process (S3).

When the thinning process is completed, the feature extracting circuit 1
2a extracts a feature point (S4), and a feature point storage memory 12b as a window image (feature pattern) together with an image in the vicinity thereof.
To be stored.

When the input of the image for registration is completed, the fingerprint image for collation is input next (S5). The fingerprint image detected by the fingerprint sensor 1 is binarized by the subsequent binarization circuit 10 (S6). Here, the fingerprint image for collation is binarized by a plurality of threshold values. The threshold value THi used is determined in step S2.
The values swung by a small amount the threshold TH _S before and after used in used. Specifically, it used multiplied by the coefficient in the reference threshold TH _S.

The binarized images are sequentially stored in the second binarization memory 13 (S7). FIG. 4A illustrates a state in which a plurality of binary images are stored. next,
Check whether the input of the image for collation is completed (S
8) If not completed, the process returns to step S5, and the binarization with another threshold value and the storing process to the memory are repeated.

When the binarization processing for all the comparison images has been completed, the operation proceeds to the feature point stability evaluation work. First, a binary image corresponding to the window image of each feature point stored in the feature point storage memory 12b (read from the first binary memory 11)
And the corresponding area of the binary image stored in the second binarization memory 13a to determine the difference in the number of white pixels (S9). The obtained difference in the number of white pixels is calculated by the stability evaluation unit 15.
Pass to. Next, it is checked whether the matching process has been completed for all the feature points (S10). Here, all the feature points mean all the feature points of the fingerprint image binarized by a plurality of threshold values.

When the collation of the number of white pixels for all the feature points is completed, the stability evaluation unit 15 takes in the difference data of the number of white pixels between the registration image and the collation image for all the feature points. . Therefore, the stability evaluation unit 15 determines the registration order of the windows based on these data (S11). That is, the ordering is performed in order from the window having the smallest change in the number of white pixels by comparison with all matching windows (S11).
This order matches the most stable feature pattern window during fingerprint matching.

When the ordering of the windows is completed, the stability evaluator 15 sends a command to the feature extractor 12, sorts and reads out from the feature point storage memory 12b in ascending order of collation error, and uses this order in the collation order. Is registered in the fingerprint dictionary storage unit 16 (S12). This means that feature points having a high appearance frequency are preferentially selected, and thus, a stable feature pattern is registered in the fingerprint dictionary storage unit 16 with respect to sweating and blurring of the finger. Will be.

When collating the fingerprint image, the collating unit 17 collates the feature pattern (window image) registered in the fingerprint dictionary 16 with the input image, and confirms the identity.

The fingerprint collation method is not limited to the above-described embodiment, and the degree evaluation unit 15 weights the window according to an excessive collation error of the binary image obtained between different binarization thresholds. May be registered in the fingerprint dictionary storage unit 16, and at the time of collation, the collation unit 17 may perform identity verification based on the magnitude of the total value of the weighted scores. By doing so, the number of windows to be compared can be reduced while maintaining a predetermined false matching rate.

The matching section 17 changes the pass / fail judgment threshold value of each window at the time of matching according to an excessive matching error between binary images obtained at different binarization threshold values. This also contributes to an improvement in the matching rate.

As a method of determining the threshold value, the average density of each of the divided small regions can be used as a reference threshold value of the plurality of binarization threshold values used in the binarization circuit 10. Further, a reference value stored in advance for each of the divided small regions may be used as a reference threshold value of the plurality of binarization threshold values used in the binarization circuit 10.

[0043]

As described above in detail, according to the present invention, all the feature points obtained from the fingerprint image for registration are stored, and the binary image for registration corresponding to these feature points is collated. By comparing a fingerprint fingerprint binary image with each other on a window basis and registering the feature patterns in ascending order of the matching error, feature points having a high appearance frequency can be preferentially selected and the processing time can be shortened. A fingerprint matching device can be provided.

[Brief description of the drawings]

FIG. 1 is a principle block diagram of the present invention.

FIG. 2 is a diagram illustrating a relationship between a fingerprint image and a fingerprint sensor output waveform.

FIG. 3 is a diagram illustrating a relationship between a binarization threshold and the number of white pixels.

FIG. 4 is a configuration block diagram showing one embodiment of the present invention.

FIG. 5 is a flowchart showing the operation of the present invention.

FIG. 6 is a conceptual diagram of a conventional fingerprint matching device.

FIG. 7 is a diagram showing an example of fingerprint feature information.

FIG. 8 is an explanatory diagram of an operation of pattern matching.

FIG. 9 is a diagram showing the registration order of windows.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Fingerprint sensor 10 Binarization circuit 11 1st binarization memory 12 Feature extraction unit 13 2nd binarization memory 14 Comparison unit 15 Stability evaluation unit 16 Fingerprint dictionary storage unit 17 Collation unit

Claims (7)

(57) [Claims] 1. A fingerprint sensor to enter a fingerprint image, receives the output of the fingerprint sensor, as compared to the multiple thresholds 2
And 2 Nekakai path was so performed to binarization, and a first binarization <br/> memory for storing the registration fingerprint image of the 2 Nekakai path, binarization of the first Note undergoing re output, a feature extraction unit for storing and extracting feature points, the second binarization memory for storing a plurality of collation fingerprint image obtained by the different thresholds of the two Nekakai path When the window image of the first binarized memory near the feature point, a second
A corresponding comparison unit for comparing the window image region of the binarized note any verification fingerprint image stored in the re of, may be stored a comparison result of the comparing unit, the feature extraction unit <br/> Stability evaluation of stored feature points as a fingerprint dictionary
Deeds, matching and stability evaluation unit for selecting feature points, and the fingerprint dictionary storage unit for storing more selected feature points in the stability evaluation unit as a fingerprint dictionary fingerprint dictionary stored in the fingerprint dictionary storage unit A fingerprint matching device comprising a matching unit that performs pattern matching with a fingerprint dictionary for use. Wherein said comparison unit, that it has to compare the number of white pixels in each window image corresponding to the first and second 2 Nekame <br/> mode Li or al minutia The fingerprint matching device according to claim 1, wherein 3. The stability evaluation unit registers in the fingerprint dictionary storage unit a registration order sorted in ascending order of a matching error between binary images obtained between different thresholds as a window use order in matching. 2. The fingerprint matching device according to claim 1, wherein the fingerprint matching is performed. 4. The stability evaluation unit weights a window according to an excessive matching error of a binary image obtained between different binarization thresholds and registers the window in a fingerprint dictionary storage unit . 2. The fingerprint matching device according to claim 1, wherein at the time of matching, the matching unit performs identity verification based on the magnitude of the total value of the weighted scores. 5. The collation unit changes a pass / fail judgment threshold of each window at the time of collation according to an excessive collation error between binary images obtained at different binarization thresholds. 2. The fingerprint matching device according to claim 1, wherein: As 6. reference threshold of a plurality of binarization threshold value used in the 2 Nekakai path, previously divided it as adapted to use the average density of each small area fingerprint identification according to claim 1, wherein apparatus. As claimed in claim 7, wherein the 2 Nekakai road reference threshold of a plurality of binarization threshold value used in, claims, characterized in that to use a reference value that has been previously allowed stored in the divided small regions each 2. The fingerprint matching device according to claim 1.